The Neo4j graph database is the fastest growing database engine in the market and has hundreds of customer references across Europe and globally, solving significant technology problems for large Enterprises in Finance, Telco, Retail, Utilities, Logistics and Internet sectors. Typical use cases are Recommendations, Fraud Detection, MDM, Network and Software Analysis and Optimization, Identity and Access Management.
17. Endpoint-Centric
Analysis of users and
their end-points!
1.
Navigation Centric
Analysis of
navigation behavior
and suspect
patterns!
2.
Account-Centric
Analysis of anomaly
behavior by channel!
3.
PC:s
Mobile Phones
IP-addresses
User ID:s
Comparing Transaction
Identity Vetting
Traditional Fraud Detection Methods
18. !
Unable to detect!
• Fraud rings!
• Fake IP-adresses!
• Hijacked devices!
• Synthetic Identities!
• Stolen Identities!
• And more…!
Weaknesses
DISCRETE ANALYSIS
Endpoint-Centric
Analysis of users and
their end-points!
1.
Navigation Centric
Analysis of
navigation behavior
and suspect
patterns!
2.
Account-Centric
Analysis of anomaly
behavior by channel!
3.
Traditional Fraud Detection Methods
20. Revolving Debt!
Number of Accounts!
Normal behavior
Fraudulent pattern
Fraud Detection with Connected Analysis
21. CONNECTED ANALYSIS
Endpoint-Centric
Analysis of users and
their end-points!
Navigation Centric
Analysis of
navigation behavior
and suspect
patterns!
Account-Centric
Analysis of anomaly
behavior by channel!
DISCRETE ANALYSIS
1.
2.
3.
Cross Channel
Analysis of anomaly
behavior correlated
across channels!
4.
Entity Linking
Analysis of relationships
to detect organized
crime and collusion!
5.
Augmented Fraud Detection
38. Show case the (near) real time fraud
detection.!
• React on fraud patterns coming in the db!
• Solution architecture!
!
• An example application showing the power of graph visualization in your
business application.!
• There are a lot of visualization products available today...!
Neo4j!
Transactions! Demo!
Application!
40. About Realtime Processing!
• For real time checking we are just as fast as in the demo even
with big databases. !
• In real time we know the transaction context. and we can jump to
the right place into the graph to find/check for fraud patterns!
!
41. Concluding!
• Effectively find Fraud Patterns because we have the Cypher Query
Language!
• We actually store the connections in the database.!
• Index Free Adjacency!
• Having the possibility to add graph-visualization to your business
applications gives you better insight in your connected data.!
MATCH (boss)-[:MANAGES*0..3]->(sub),
(sub)-[:MANAGES*1..3]->(report)
WHERE boss.name = “John Doe”
RETURN sub.name AS Subordinate,
count(report) AS Total
42. Anti Money Laundering!
• Seeking for deep patterns (who sends money to who)!
• Using also shared attributes like in Fraud Rings: !
• Names!
• Email!
• Phone!
• Address!
• SSN!
• IDNO....!
• Transaction Context!
45. Money
Transferring!
Purchases! Bank
Services! Relational
database
Data Lake
+ Good for Map Reduce
+ Good for Analytical Workloads
– No holistic view
– Non-operational workloads
– Weeks-to-months processes Develop Patterns!
Data Science-team
Merchant
Data!
Credit
Score
Data!
Other 3rd
Party
Data!
46. Money
Transferring!
Purchases! Bank
Services!
Neo4j powers
360° view of
transactions in
real-time
Neo4j
Cluster
SENSE
Transaction
stream
RESPOND
Alerts &
notification
LOAD RELEVANT DATA
Relational
database
Data Lake
Visualization UI
Fine Tune Patterns
Develop Patterns!
Data Science-team
Merchant
Data!
Credit
Score
Data!
Other 3rd
Party
Data!
47. Money
Transferring!
Purchases! Bank
Services!
Neo4j powers
360° view of
transactions in
real-time
Neo4j
Cluster
SENSE
Transaction
stream
RESPOND
Alerts &
notification
LOAD RELEVANT DATA
Relational
database
Data Lake
Visualization UI
Fine Tune Patterns
Develop Patterns!
Data Science-team
Merchant
Data!
Credit
Score
Data!
Other 3rd
Party
Data!
Data-set used
to explore
new insights
48. Concluding!
• The Neo4j graph database is a natural fit for finding fraud patterns in
the data in real time (and non-real time)!
Delayed Data
Analysis!
Real Time Connected
Analysis!